mlsanityData to 7 Oct 2026

Visual Explanations from Spiking Neural Networks using Interspike Intervals

arXiv 2103.14441 ↗First posted 26 Mar 2021cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) compute and communicate with asynchronous binary temporal events that can lead to significant energy savings with neuromorphic hardware. Recent algorithmic efforts on training SNNs have shown competitive performance on a variety of classification tasks. However, a visualization tool for analysing and explaining the internal spike behavior of such temporal deep SNNs has not been explored. In this paper, we propose a new concept of bio-plausible visualization for SNNs, called Spike Activation Map (SAM). The proposed SAM circumvents the non-differentiable characteristic of spiking neurons by eliminating the need for calculating gradients to obtain visual explanations. Instead, SAM calculates a temporal visualization map by forward propagating input spikes over different time-steps. SAM yields an attention map corresponding to each time-step of input data by highlighting neurons with short inter-spike interval activity. Interestingly, without both the backpropagation process and the class label, SAM highlights the discriminative region of the image while capturing fine-grained details. With SAM, for the first time, we provide a comprehensive analysis on how internal spikes work in various SNN training configurations depending on optimization types, leak behavior, as well as when faced with adversarial examples.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 31 of its 72 references that are in the map. First posted on arXiv 26 Mar 2021.

Builds on

31 of 72 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  8. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  9. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  10. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  11. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  12. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
19 more
  1. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  2. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  3. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 203
  4. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  5. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  6. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 141
  7. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 119
  8. 2018Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontierscited by 117
  9. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 76
  10. 2016Supervised learning based on temporal coding in spiking neural networkscited by 75
  11. 2019S4NN: temporal backpropagation for spiking neural networks with one spike per neuroncited by 47
  12. 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 47
  13. 2019Temporal Coding in Spiking Neural Networks with Alpha Synaptic Function: Learning with Backpropagationcited by 43
  14. 2019A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networkscited by 35
  15. 2018Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networkscited by 34
  16. 2019Combinational Class Activation Maps for Weakly Supervised Object Localizationcited by 24
  17. 2019Parameter Optimization and Learning in a Spiking Neural Network for UAV Obstacle Avoidance targeting Neuromorphic Processorscited by 11
  18. 2020Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labelscited by 10
  19. 2016A Self-Driving Robot Using Deep Convolutional Neural Networks on Neuromorphic Hardwarecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 9; 2023: 4; 2024: 2; 2025: 3; 2026: 3.

26 papers.

Sort:

  1. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  2. 2022Attention Spiking Neural Networkscited by 103
  3. 2021Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentationcited by 54
  4. 2022Neural Architecture Search for Spiking Neural Networkscited by 52
  5. 2022Exploring Lottery Ticket Hypothesis in Spiking Neural Networkscited by 25
  6. 2022Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?cited by 24
  7. 2022Exploring Temporal Information Dynamics in Spiking Neural Networkscited by 23
  8. 2021Federated Learning with Spiking Neural Networkscited by 22
  9. 2021Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networkscited by 22
  10. 2021PrivateSNN: Privacy-Preserving Spiking Neural Networkscited by 15
  11. 2022Deep Reinforcement Learning with Spiking Q-learningcited by 15
  12. 2022Toward Robust Spiking Neural Network Against Adversarial Perturbationcited by 12
14 more
  1. 2023LaSNN: Layer-wise ANN-to-SNN Distillation for Effective and Efficient Training in Deep Spiking Neural Networkscited by 11
  2. 2023Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradientcited by 11
  3. 2023Adversarially Robust Spiking Neural Networks Through Conversioncited by 7
  4. 2024EventRPG: Event Data Augmentation with Relevance Propagation Guidancecited by 7
  5. 2024ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognitioncited by 3
  6. 2021Continual learning under domain transfer with sparse synaptic burstingcited by 1
  7. 2022A Novel Explainable Out-of-Distribution Detection Approach for Spiking Neural Networkscited by 1
  8. 2025Explainable AI the Latest Advancements and New Trendscited by 1
  9. 2023Feature Attribution Explanations for Spiking Neural Networkscited by 0
  10. 2025SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networkscited by 0
  11. 2025A Closer Look at Knowledge Distillation in Spiking Neural Network Trainingcited by 0
  12. 2026Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularizationcited by 0
  13. 2026Native Explainability for Bayesian Confidence Propagation Neural Networks: A Framework for Trusted Brain-Like AIcited by 0
  14. 2026Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networkscited by 0